© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 157529
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ವರ್ಗ
    0.41
    สาร
    0.39
    江湖
    0.38
    Jessica
    0.38
    Sà
    0.38
    /////
    0.38
     bû
    0.37
    ník
    0.36
    nam
    0.36
    ंबर्स
    0.35
    POSITIVE LOGITS
     Stephenson
    0.43
     Care
    0.42
     Tory
    0.42
     Morn
    0.41
    롭
    0.41
     Marlin
    0.41
    ibin
    0.40
     CARE
    0.40
     Stephan
    0.40
     Zach
    0.39
    Activations Density 0.005%

    No Known Activations